39results about How to "Effective obstacle avoidance" patented technology

The invention relates to a moving robot obstacle avoiding method based on a laser range finder, which comprises the following steps: building the coordinate system of the robot; with the current location of the robot as a center of a circle, simulating laser transmission at the origin of coordinates to transmit N laser beams of which the directions are determined as candidate directions of the motion of the robot; dividing laser information into groups, selecting an obstacle point in each group, and mapping the obstacle point into the coordinate system of the robot; expanding the robot into acircle with a radius of R, drawing two tangent lines of the circle through one obstacle point, working out the range of the candidate directions in which the robot can go across the obstacle point according to the included angles of the tangent lines and an X-axis, and getting the direction in which the robot can go across the obstacle point; defining a cost function to evaluate all feasible directions, and selecting the optimal direction of the next circle of motion of the robot; and working out the linear speed and angular speed of the robot by using a speed control policy. According to themethod, the robot can avoid an obstacle in an unknown environment, and has high performance; and without deeper theoretical foundation, the method is simple, smart, easy to understand and practical, requires small calculation, and is particularly suitable to use.

The invention discloses an obstacle identification method. The method comprises the following steps: acquiring a first depth image of a surrounding environment in a driving route; performing cutting processing on the first depth image to obtain a second depth image corresponding to the driving lane; performing ground fitting based on the second depth image, determining a ground straight line, removing a ground part according to the ground straight line, and obtaining a third depth image without the ground part; and performing clustering analysis on the third depth image, obtaining a pluralityof obstacle clustering point sets, and determining position information of each obstacle. Correspondingly, the invention further discloses an obstacle identification system. According to the invention, the obstacle is monitored in real time, and the obstacle can be better avoided.

The invention relates to a continuous frame based blind guiding instrument combination path planning method. Specifically, for each frame shot by a binocular camera, global path preview tracking is conducted to determine a local planning target point, local path planning is carried out according to the environmental information detected by the camera in real time, a walking direction error angle is output to induce the blind to walk till reaching a global target point. During local path planning, grid visualization is firstly conducted on the environmental information of a current frame, then the A* algorithm is employed for local path planning, and finally a re-weighting method path conversion method is employed to calculate the angular deviation of the current frame walking direction and a local planned path to serve as the input information of a controller for inducing the blind to walk. The invention designs a novel blind guiding instrument combination path planning method, the method can realize real-time path planning, and provides the necessary foundation for guiding the blind to follow the blind pass to walk in the premise of avoiding obstacles and arrive at the destination finally.

The invention discloses an intelligent cruise control system for a vehicle and a control method thereof. The intelligent cruise control system for the vehicle comprises a cruise control switch, a speed sensor, a forward vehicle detecting radar, a main controller and a throttle valve driving module; the main controller is connected with a signal processing module; the cruise control switch, the speed sensor, the forward vehicle detecting radar, a left side detecting radar, a right side detecting radar and a following vehicle detecting radar are connected to the signal processing module; a weather detecting module and a tire pressure detecting sensor are also connected to the signal processing module; a display screen, the throttle valve driving module, a cruise indicator lamp driving module and a speech driving module are all connected to the main controller; the main controller is connected with an image processing module; and a first camera and a second camera are connected to the image processing module. According to the intelligent cruise control system for the vehicle, the cruise state of the vehicle can be optimized according to environment factors and running statues of surrounding vehicles.

The invention discloses a balance car indoor positioning and navigation itinerant system based on a single-line laser radar. The balance car indoor positioning and navigation itinerant system comprises a server, an upper computer, a sensor, a motion controller and a motion actuator. Firstly, an operator inputs coordinates of a target point in the server; the server sends the coordinates of the target point to the upper computer, the upper computer uses sensor information to complete self-positioning and path planning of the balance car, and the upper computer sends the expected angular velocity and the expected linear velocity planned by the path to the motion controller; the motion controller receives information sent by the upper computer, collects sensor information at the same time, calculates a PWM wave duty ratio required by the motion actuator by using the information in combination with an active disturbance rejection control method, and then sends the PWM wave to the motion actuator; after the motion actuator receives the PWM waves, the balance car is driven to run to a target point while self-balancing of the balance car is completed; finally, the operator can see the real-time position and state information of the map and the balance car on the server.

The invention provides a mechanical arm control method. The mechanical arm control method comprises the steps that obstacle information associated with a mechanical arm is obtained; the current pose information of the mechanical arm is obtained, and the tail end expected pose information of the mechanical arm is obtained; according to the obstacle information, the current pose information, the tail end expected pose information and a preset dynamic system model function, a tail end expected track of the mechanical arm is determined; according to the tail end expected track, the tail end expected speed of the mechanical arm is determined; according to the obstacle information and the current pose information of the mechanical arm, the virtual speed of a target point on the mechanical arm is determined, and the target point is the point, closest to an obstacle, on the mechanical arm; and according to the virtual speed and the tail end expected speed, the target joint speed corresponding to a target joint of the mechanical arm is determined. According to the mechanical arm control method, the redundant mechanical arm can effectively avoid obstacles in the application environment with various obstacles and can execute corresponding tasks at the same time.

The invention belongs to the technical field of unmanned driving and discloses a multiple sensor-integrated medium-speed unmanned vehicle detection and obstacle avoidance system, which comprises a control system, a vehicle roof laser radar, a vehicle-mounted monocular vision camera, a front laser radar group and a rear laser radar group, wherein the vehicle roof laser radar is used for detecting ups and downs of a road in front of the unmanned vehicle and together with the front laser radar group, detecting the obstacle condition in a front motion path of the unmanned vehicle; the front laserradar group is also used for detecting the obstacle condition in a left front motion path and a right front motion path of the unmanned vehicle; the rear laser radar group is used for detecting the obstacle condition in the rear side of the unmanned vehicle; the vehicle-mounted monocular vision camera is used for recognizing a sign in front of the unmanned vehicle and together with the vehicle roof laser radar and the front laser radar group in match, detecting the obstacle condition; and the control system comprises an upper computer and a lower computer; and the lower computer is a dual-corecontroller formed by an FPGA and an ARM. The price is low, the cost performance is relatively high, and the practicability is strong.

The invention discloses a virtual reality device and an obstacle avoidance method provided by the virtual reality device. According to the virtual reality device and the obstacle avoidance method, a calculation module of the virtual reality device gives an obstacle avoidance instruction according to relative movement speed of the virtual reality device and an obstacle, distance between the virtual reality device and the obstacle at a second time point and acceleration speed of the virtual reality device at the second time point, so that a virtual reality device user can be guided to avoid the obstacle effectively, and experience satisfaction is good.

The invention provides a multi-sensor fused unmanned vehicle detection obstacle avoidance system and obstacle avoidance method. The obstacle avoidance system comprises a plurality of single-line laserradars, double CCD cameras, microwave radars, front and rear blind area ultrasonic sensor groups and a three-core controller based on ARM + FPGA + NUC. A plurality of single-line laser radar signalsare processed by the NUC microcomputer, binocular vision graphic data of the CCD camera are jointly processed by the ARM + FPGA controller, functions of blind area detection and obstacle avoidance, ahuman-computer interface, path planning, online output and the like are independently completed by the STM32F767, and the ARM + FPGA controller outputs control signals through decoding to accurately control the direct-current brushless servo motor, and drives an unmanned vehicle to run. According to the invention, the unmanned vehicle can discover obstacles in a complex environment in an all-weather and farther manner and quickly realize effective obstacle avoidance, so the safety and stability of the unmanned vehicle during high-speed driving are improved.

The invention relates to an autonomous mobile selling truck and an obstacle avoidance method thereof. The method comprises the following steps: obtaining visual data of a visual sensor, millimeter wave radar data and ultrasonic radar data; converting the position of obstacles in visual data to the coordinate system of millimeter wave radar, and the data is fused with the millimeter wave radar datato obtain the first fused data. The millimeter wave radar data and the ultrasonic radar data are fused to obtain the second fused data; according to the first fused data and the second fused data, adeceleration stop signal or an immediate stop signal is output. As that application utilize the characteristics of different sensor to collect obstacle information in different distances respectively,a deceleration region and a dangerous region are designed by multi-sensor data fusion, and different data are used for decision-making in different regions, so that obstacle avoidance is more effective. At the same time, since the mode of immediate stopping is adopted in the dangerous area, the safety of the autonomous mobile sales trucks is greatly improved, and the collision can be avoided in the emergency.

Embodiments of the invention disclose an unmanned airship avoidance system and an unmanned airship flight control system. The unmanned airship avoidance system comprises an environment perception module, an avoidance module and multiple perception sensors, wherein the perception sensors detect perception information of an unmanned airship and transmits the perception information to the environmentperception module; the environment perception module performs fusion, analysis and cognitive processing on weighted information corresponding to the received perception information according to the current environment and weight values of the perception sensors in different environments, and transmits obtained analysis result information to the avoidance module; and the avoidance module judges whether avoidance operation is executed or not according to the received analysis result information, and sends a control instruction used for executing the avoidance operation to the flight control system after the avoidance operation is confirmed to be executed. According to the unmanned airship avoidance system and the unmanned airship flight control system, the problem that an existing unmannedairship cannot perceive the surrounding environment and avoid obstacles because flight of the existing unmanned airship is controlled only through a flight control computer is solved.

The embodiment of the invention provides a mobile robot obstacle avoidance method and device and a mobile robot. Firstly, an obstacle detection signal is emitted and a reflection signal of an obstacleis received, a reflection signal sent by a mobile robot is received, the reflection signal intensity corresponding to the reflection signal is obtained, an obstacle detection mode is determined basedon the reflection signal intensity and a preset condition, and finally the motion state of the mobile robot is controlled according to the obstacle detection mode and the real-time reflection signal.According to the method, when the mobile robot works in the path planned by a user, obstacles on the path are effectively avoided, the risk that the mobile robot collides with the wall is reduced, and then the service life of the mobile robot is prolonged.

The invention belongs to the technical field of unmanned driving and discloses a multi-sensor-fused low-speed unmanned vehicle detecting obstacle avoidance system. The multi-sensor-fused low-speed unmanned vehicle obstacle avoidance system comprises a control system and a vehicle roof laser radar and further comprises a front laser radar set and a back laser radar set which are configured on the lower portion of an unmanned vehicle body. The vehicle roof laser radar is used for detecting fluctuation of a road in front of an unmanned vehicle and detecting the condition of obstacles in a movement path in front of the unmanned vehicle with the front laser radar set. The front laser radar set is further used for detecting the condition of obstacles in a front left movement path and a front right movement path of the unmanned vehicle. The back laser radar set is used for detecting the condition of obstacles behind the unmanned vehicle. The control system comprises an upper computer and a lower computer, the upper computer receives feedback signals of all the laser radars in real time, conducts decoding, then communicates with the lower computer and transmits input control signals to thelower computer, and the lower computer decodes the input control signals to control travelling of the unmanned vehicle. The multi-sensor-fused low-speed unmanned vehicle obstacle avoidance system islow in price, relatively high in cost performance, and very high in practicability.

The invention discloses a blind sidewalk detection device which is used for carrying out the following processes: sampling through a sensor at regular intervals to obtain angles of a carrier, and carrying out differentiation on the angles sampled at adjacent moments to obtain the angle variation of the carrier within the period of time; summing the angle difference negative feedback, the angle variation and the compensation quantity of a previous cycle to obtain the adjustment amount; judging the value of the angle variation of the carrier before adjustment of a stepper motor, and adaptively changing the sampling rate; and making the adjustment quantity participate into the next cycle as the compensation quantity when judging that the adjustment quantity is over-small. A detector can be adjusted in real time by using the stepper motor to keep the required detection direction, so that the detection result is more accurate; the adjustment rate can be adaptively changed, so that the adjustment range of the detector is reduced as far as possible, a more stable detection direction is achieved, and the anti-jamming capability is high; and the step lost phenomenon caused by too small adjustment quantity and a too small pulse number of the stepper motor can be prevented, and an accurate control effect is achieved.

The invention discloses a modular intelligent visual impairment auxiliary system, being characterized in that the intelligent visual impairment auxiliary system includes an indoor positioning module, an outdoor positioning module, an obstacle avoidance module, an identification module and an interaction module; the intelligent visual impairment auxiliary system is constructed by adopting each functional module; and effective information in a complex application scene is accurately obtained and accurate and comprehensive transmission is realized through information acquired by different sensors, so that visual impairment assistance in different environments is met, and the functions of indoor and outdoor positioning, obstacle avoidance and the like are realized. Compared with the prior art, the modular intelligent visual impairment auxiliary system has the functions of indoor and outdoor positioning, interactive reading and the like, can accurately obtain effective information in a complex application scene and accurate and comprehensive transmission so as to satisfy visual impairment assistance in different environments, and help visual impairment people to effectively avoid obstacles; and the modular intelligent visual impairment auxiliary system is simple in structure, convenient to use and high in reliability.

The invention discloses a laser ranging method, which comprises the steps of controlling a plurality of laser emission sources to emit light spots to different directions in sequence, and projecting the light spots to a measured object; controlling a receiving device to receive the light information of the light spot every time the light spot projection is completed; and calculating the distance from the laser emission source to the measured object according to the light information. Light spots are emitted to different directions through the emission source, so that multi-angle detection of afront obstacle is realized, the light information of the light spots projected at each angle is processed and calculated, the detection precision is improved while the distance from the laser emission source to a measured object is obtained, and the obstacle can be effectively avoided.

The invention discloses a bionic scorpion robot, and belongs to the technical field of bionic equipment. The bionic scorpion robot comprises a trunk, six walking foot units, two clamp part units, two detection units and a control part, wherein the six walking foot units are symmetrically arranged on the two sides of the bottom of the trunk, and the walking foot units are used for executing walking actions; the two clamp part units are symmetrically arranged on the two sides of the bottom of the front end of the trunk, and the clamp part units are used for executing the grabbing action; the two detection units are arranged on the two sides of the top of the front end of the trunk, and each detection unit comprises an infrared probe and a sound wave receiver; and the control part is arranged on the top face of the middle of the trunk, the control part controls all the units to execute corresponding actions, and a sound wave generator is further arranged on the control part. Through the infrared probes of the detection units, the bionic scorpion robot can adapt to the environment with poor light, the investigation and observation capacity of the robot is improved, meanwhile, the robot can effectively avoid obstacles and improve the emergency capacity of the robot in cooperation with sound wave detection, and the robot can adapt to most of land environment terrains in combination with the design of the walking foot unit.

The invention discloses an obstacle avoiding method for a robot and robot equipment. According to the obstacle avoiding method, the robot can effectively avoid an obstacle by acquiring an image of a surrounding environment of the obstacle through a camera, generating a peripheral rectangle of the obstacle according to the image of the surrounding environment of the obstacle, and generating, according to position information of a starting point, a target object and the obstacle, an NURBS curve to serve as an obstacle avoiding path, so that the robot can avoid the obstacle effectively.

The embodiment of the invention provides a collision processing method and device, sweeping equipment and a computer readable storage medium, and the method comprises the steps: obtaining a detectionsignal outputted by a collision detection part, wherein the collision detection part is used for detecting whether there is an obstacle in a preset region or not; determining a collision position according to the detection signal; and carrying out obstacle avoidance processing according to the collision position. According to the method, the collision position of the radome can be judged accordingto the detection signal output by the collision detection component, and the sweeping equipment is controlled to carry out targeted obstacle avoidance processing according to the collision position,so that the obstacle can be effectively avoided.

The invention discloses a vehicle obstacle avoidance method and apparatus, an electronic device and a storage medium. The method comprises steps of obtaining continuous multiple frames of images; determining the motion information of a target object in the images based on the continuous multiple frames of images, and extracting the current pose information of the vehicle; determining the motion information of each pixel in a pixel set corresponding to the current image based on the current image in the continuous multiple frames of images; correcting the current pose information according to the motion information of each pixel in the pixel set; updating the motion information of each pixel based on the corrected pose information and the motion information of the target object to obtain the updated motion information of each pixel; determining dangerous pixels from the pixel set based on the driving space information of the vehicle and the space information of each pixel; and indicating the vehicle to perform obstacle avoidance reaction based on the motion information of the dangerous pixels. The method is advantaged in that more effective obstacle avoidance indication can be obtained by combining the motion information of the target object and the pixel, and safety of the vehicle can be improved.

The invention relates to an unmanned aerial vehicle autonomous path planning method, and belongs to the technical field of unmanned aerial vehicle control. The unmanned aerial vehicle hybrid path planning method is improved on the basis of an existing ADA * algorithm, time consumption caused by repeated sorting is reduced, meanwhile, for unmanned aerial vehicle obstacle avoidance, a local planning neural network based on DRL is additionally adopted, existing obstacles are detected, a path is re-planned, the calculation load of an airborne computer is greatly reduced, and obstacles can be effectively avoided.

The embodiment of the present application provides a robot and a steering control method thereof, wherein the robot is provided with a first driving wheel and a second driving wheel that can realize the steering of the robot through differential rotation, and the method includes: acquiring a current yaw angle of the robot . The first adjustment amount of the first driving wheel and the second driving wheel is calculated according to the current yaw angle and the target yaw angle. Acquire the current actual rotational speed of the first driving wheel and the second driving wheel. A second adjustment amount of the first driving wheel and the second driving wheel is calculated according to the current actual rotational speed. The actual adjustment amounts of the first driving wheel and the second driving wheel are calculated according to the first adjustment amount and the second adjustment amount. In the above manner, the present application can ensure the accuracy of the robot rotation control.

The invention discloses an autonomous obstacle avoidance and navigation method for a quadcopter based on a binocular camera. The matching point pairs in two adjacent frames of images are processed through an ICP algorithm, so that the quadcopter can achieve precise positioning, and at the same time generate an image that can accurately characterize the surroundings. A dense map of the environment. Then convert the dense map into an octree map suitable for collision detection algorithms, and obtain the obstacle constraints required by the improved RRT* algorithm through the feedback results of the collision detection between the quadcopter and the octree map, and then real-time Plan possible paths. When the quadcopter flies along the planned path, it can successfully avoid obstacles and reach the preset end point.

The invention discloses an obstacle avoidance method of a multi-rotor unmanned aerial vehicle. The method comprises the following steps that: when an unmanned aerial vehicle flies, a laser radar detection device is activated by means of flight control; when the laser radar detecting device detects obstacle occurrence in front of the unmanned aerial vehicle, an unmanned aerial vehicle flight control unit controls the unmanned aerial vehicle to make horizontal and vertical translation to calculate distance and size information of the obstacle. The method is simple and effective; the collision probability of the unmanned aerial vehicle is reduced; and the application efficiency of the battery is increased.

The invention relates to an intelligent cloud simulation obstacle avoidance system for a wheelchair. The system comprises a cloud processor, a drone and the wheelchair, the wheelchair comprises a processing device, a driving motor and a first camera, and the drone comprises a CPU chip and a photography device; the cloud processor, the processing device and the CPU chip are in data synchronization,the cloud processor comprises a three-dimensional real-scene simulation module and a calculation module, the cloud processor judges whether or not reversing is needed according to the size ratio of the obstacle distance in a generated three-dimensional real-scene simulation graph to the preset distance, and if yes, the driving motor is driven to control the wheelchair to reverse. According to theintelligent cloud simulation obstacle avoidance system for the wheelchair, three-dimensional real-scene is processed through the cloud processor, the first visual angle of a user is simulated to a great extent, obstacle judgement and distance calculation are conducted according to the simulated first visual angle, and accordingly obstacle avoidance can be conducted more effectively.

The invention discloses a wheel type obstacle crossing robot chassis which comprises a chassis body; a driving wheel which is rotatably supported on the chassis main body; a mounting frame, wherein one end of the mounting frame is detachably connected with the chassis main body; an obstacle crossing wheel which is rotatably supported at the other end of the mounting frame; an obstacle crossing assembly which is arranged between the mounting frame and the obstacle crossing wheel and can enable the obstacle crossing wheel to slide along the mounting frame so as to climb over an obstacle; and a laser radar navigation module which is connected with the chassis main body and is used for obstacle identification and path planning. The obstacle crossing assembly is arranged between the obstacle crossing wheel and the chassis body, the obstacle crossing wheel can slide up and down and climb over the obstacle, the structure is simple, meanwhile, the invention further provides a method for recognizing the obstacle and planning the path through the robot chassis, and the advancing efficiency of the robot chassis is improved by updating the environment map and optimizing the path in real time.

The invention discloses an obstacle identification method, the method comprising: acquiring a first depth image of the surrounding environment in a driving route; performing cutting processing on the first depth image to obtain a second depth image corresponding to the driving lane; based on Perform ground fitting on the second depth image, determine the ground straight line, and remove the ground part according to the ground straight line to obtain a third depth image without the ground part; perform cluster analysis on the third depth image to obtain multiple Obstacle cluster point set, and determine the position information of each obstacle. Correspondingly, the invention also discloses an obstacle recognition system. Through the present invention, obstacles can be monitored in real time, and obstacles can be better avoided.

The invention provides a system and method for unmanned aerial vehicle inspection and obstacle avoidance of power transmission lines. The system includes an interconnected environment perception module and an obstacle avoidance main control terminal. The information data is sent to the obstacle avoidance main control terminal, and the obstacle avoidance main control terminal performs fusion processing on the environmental information data, performs SLAM calculation according to the fused data, and updates the drone according to the SLAM calculation result and the preset drone track planning Track planning. The whole system can sense the position of obstacles around the UAV, perform SLAM calculations based on the fused data, and update the UAV trajectory planning based on the SLAM calculation results and the preset UAV trajectory planning, which can effectively target unknown obstacles Avoid obstacles.